{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T12:32:24Z","timestamp":1770813144932,"version":"3.50.1"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276120"],"award-info":[{"award-number":["62276120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019410","name":"Yunnan Fundamental Research Projects","doi-asserted-by":"publisher","award":["202301AV070004"],"award-info":[{"award-number":["202301AV070004"]}],"id":[{"id":"10.13039\/501100019410","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019410","name":"Yunnan Fundamental Research Projects","doi-asserted-by":"publisher","award":["202401AS070640"],"award-info":[{"award-number":["202401AS070640"]}],"id":[{"id":"10.13039\/501100019410","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3658218","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T20:46:59Z","timestamp":1770065219000},"page":"1423-1435","source":"Crossref","is-referenced-by-count":0,"title":["Bidirectional Cross-Modal Collaborative Alignment via Semantic-Guided Visual Embeddings for Partially Relevant Video Retrieval"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2462-6174","authenticated-orcid":false,"given":"Huafeng","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0086-6946","authenticated-orcid":false,"given":"Jialong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2347-5642","authenticated-orcid":false,"given":"Yafei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9554-2379","authenticated-orcid":false,"given":"Jie","family":"Wen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-023-00267-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01427"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02242"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01107"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_24"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3565981"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28389"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00338"},{"key":"ref10","first-page":"21789","article-title":"Prototypes are balanced units for efficient and effective partially relevant video retrieval","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Moon"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3590937"},{"key":"ref12","first-page":"23074","article-title":"Enhancing partially relevant video retrieval with hyperbolic learning","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3630883"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01038"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3716388"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32252"},{"key":"ref17","first-page":"1786","article-title":"W2vv++ fully deep learning for ad-hoc video search","volume-title":"Proc. 27th ACM Int. Conf. Multimedia","author":"Li"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3257193"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01820"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01622"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00635"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref27","first-page":"24564","article-title":"Prototype-based aleatoric uncertainty quantification for cross-modal retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref28","article-title":"CLIP2TV: Align, match and distill for video-text retrieval","author":"Gao","year":"2021","journal-title":"arXiv:2111.05610"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0127"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02538"},{"key":"ref34","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Akbari"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2024.104235"},{"key":"ref36","first-page":"22263","article-title":"Bidirectional likelihood estimation with multi-modal large language models for text-video retrieval","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Ko"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref40","first-page":"281","article-title":"Some methods of classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Stat. Prob.","author":"McQueen"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475281"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref47","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"arXiv:1912.01703"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772862"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2307\/2984875"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11370453.pdf?arnumber=11370453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T05:57:21Z","timestamp":1770789441000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11370453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3658218","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}